{"id":"W4313122446","doi":"10.1109/tdei.2022.3215936","title":"Accurate Identification of Transformer Faults From Dissolved Gas Data Using Recursive Feature Elimination Method","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Dielectrics and Electrical Insulation","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Dissolved gas analysis; Feature selection; Support vector machine; Unavailability; Oversampling; Benchmark (surveying); Artificial intelligence; Computer science; Pattern recognition (psychology); Data mining; Extreme learning machine; Transformer; Machine learning; Engineering; Reliability engineering; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000377907,0.0005452389,0.0005610719,0.000985734,0.0001781554,0.0004047198,0.0004214712,0.000365168,0.0004222787],"category_scores_gemma":[0.001201475,0.0001282051,0.0004218131,0.0005293891,0.0001149671,0.0004416411,0.0002421172,0.0003633132,0.0002709634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002503994,"about_ca_system_score_gemma":0.0003772502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004123518,"about_ca_topic_score_gemma":0.002837861,"domain_scores_codex":[0.999822,0.0000255689,0.00001466905,0.00004890974,0.00005941377,0.00002961212],"domain_scores_gemma":[0.9996451,0.000113967,0.00005436914,0.00003133552,0.0001449318,0.00001033805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004999654,0.0002229973,0.01374935,0.000144851,0.0000730084,0.0004044851,0.0001532805,0.2613415,0.09655001,0.0013886,0.002528851,0.622943],"study_design_scores_gemma":[0.000006380582,0.0000320921,0.003553135,0.000002896576,0.00000837226,0.00004487962,0.00001702855,0.9843636,0.01135088,0.0002415898,0.0003723614,0.000006703955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3005476,0.0002531406,0.6954646,0.0000989086,0.00003462367,0.00007026042,0.0003465322,0.002116205,0.001068127],"genre_scores_gemma":[0.8942066,0.00009587627,0.1042778,0.00001674386,0.00001282703,0.00005351858,0.0006154107,0.00003635622,0.0006849103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004123518,"threshold_uncertainty_score":0.008199036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03097162683829959,"score_gpt":0.2855028695134273,"score_spread":0.2545312426751277,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}